Alibaba (Qwen) · model
Qwen3 235B 2507 benchmark scores
As of 2026-11-22, Qwen3 235B 2507 (Alibaba (Qwen)) has measured scores on 9 benchmarks and estimated scores on 37 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 83.1% | estimated ± 3.7 pp, high confidence |
| AA-HLE | 13.7% | estimated ± 5.7 pp, medium confidence |
| AA-SciCode | 17.5% | estimated ± 4.7 pp, medium confidence |
| AIME26 | 71.4% | estimated ± 4.3 pp, medium confidence |
| Artificial Analysis Intelligence Index | 18.0% | estimated ± 3.0 pp, high confidence |
| CritPt | 0.4% | estimated ± 4.0 pp, high confidence |
| GPQA Diamond | 77.7% | estimated ± 1.2 pp, high confidence |
| HLE | 16.9% | estimated ± 5.1 pp, medium confidence |
| IFBench | 62.5% | estimated ± 9.2 pp, medium confidence |
| LiveCodeBench v6 | 51.8% | measured |
| AA-Omniscience Accuracy | 27.5% | estimated ± 6.7 pp, low confidence |
| SciCode | 17.7% | estimated ± 4.9 pp, medium confidence |
| IFEval | 88.7% | measured |
| AA Coding Index | 6.7% | estimated ± 5.7 pp, medium confidence |
| SWE-bench Verified | 57.5% | estimated ± 9.7 pp, low confidence |
| SWE-bench Pro | 0.0% | estimated ± 6.0 pp, low confidence |
| MMLU-Pro | 83.0% | measured |
| AA-IFBench | 44.0% | estimated ± 8.8 pp, medium confidence |
| AIME 2024 | 80.2% | estimated ± 2.6 pp, high confidence |
| BBH | 97.7% | estimated ± 2.8 pp, medium confidence |
| FailureSensorIQ | 60.8% | measured |
| GPQA | 77.5% | measured |
| MMLU | 89.8% | estimated ± 2.1 pp, high confidence |
| Vals GPQA Diamond | 75.3% | estimated ± 4.5 pp, high confidence |
| Vals MMLU-Pro | 82.1% | estimated ± 2.3 pp, high confidence |
| MATH-500 | 95.9% | estimated ± 2.0 pp, high confidence |
| MMMLU | 86.0% | estimated ± 1.7 pp, high confidence |
| AIME 2025 | 70.3% | measured |
| AA MMLU-Pro | 85.8% | estimated ± 1.2 pp, low confidence |
| ARC-AGI-1 | 43.5% | estimated ± 6.7 pp, low confidence |
| ARC-AGI-2 | 0.0% | estimated ± 10.9 pp, low confidence |
| HLE w/o tools | 12.6% | estimated ± 5.3 pp, medium confidence |
| SWE Multilingual | 65.7% | estimated ± 3.2 pp, low confidence |
| BinaryAudit | 8.2% | estimated ± 8.9 pp, low confidence |
| OTelBench | 3.5% | estimated ± 7.7 pp, low confidence |
| C-Eval | 89.1% | estimated ± 1.0 pp, low confidence |
| HMMT Feb 2025 | 64.0% | estimated ± 2.9 pp, medium confidence |
| HMMT Feb 2026 | 35.2% | estimated ± 11.0 pp, low confidence |
| INCLUDE | 81.6% | estimated ± 1.4 pp, low confidence |
| MAXIFE | 66.4% | estimated ± 6.5 pp, low confidence |
| MMLU-ProX | 79.4% | measured |
| MMLU-Redux | 92.1% | estimated ± 0.6 pp, high confidence |
| NOVA-63 | 54.9% | estimated ± 1.3 pp, low confidence |
| PolyMath | 38.4% | estimated ± 11.4 pp, low confidence |
| SuperGPQA | 62.6% | measured |
| SimpleQA | 54.3% | measured |